Output tokens cost $0.31 per million on deepseek-v4-flash and $12.00 per million on gemini-3.1-pro-preview. Input tokens cost $0.15 per million on deepseek-v4-flash and $2.00 per million on gemini-3.1-pro-preview. Cached input tokens are billed at $0.00 per million on deepseek-v4-flash and $0.50 per million on gemini-3.1-pro-preview. Context windows are 1,000,000 tokens on deepseek-v4-flash and 1,000,000 tokens on gemini-3.1-pro-preview. First-token latency measured on AIHubMix is 1.2s on deepseek-v4-flash and 5.9s on gemini-3.1-pro-preview. Measured output throughput is 101.3 tokens/s on deepseek-v4-flash and 79.5 tokens/s on gemini-3.1-pro-preview.
deepseek-v4-flash
gemini-3.1-pro-previewDeepSeek-V4 features an ultra-long context of one million characters and achieves leading performance domestically and in the open-source domain in agent capabilities, world knowledge, and reasoning.
Gemini 3.1 Pro Preview is designed to further optimize the performance and reliability of the Gemini 3 Pro series, offering improved reasoning capabilities, greater token efficiency, and a more robust, factually consistent user experience. It is optimized for software-engineering behaviors and usability, and is also suitable for agent workflows that require precise tool invocation and reliable multi-step execution, enabling stable operation across a variety of real-world scenarios.
Prices are per million tokens. Latency and throughput are rolling averages measured on AIHubMix.
Promotional prices show the discounted rate; see each model page for promotion windows.
Daily traffic served through AIHubMix — how demand for each model is trending.
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
Estimate your monthly bill for the same workload on each model.
Monthly = daily × 30. Discounted rates applied where a promotion is active.
deepseek-v4-flash: $0.31/M output tokens; gemini-3.1-pro-preview: $12.00/M. Use the cost calculator above to estimate your own workload.
deepseek-v4-flash: 1.2s first-token latency measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
deepseek-v4-flash accepts 1,000,000 and gemini-3.1-pro-preview accepts 1,000,000 input tokens. Maximum output per request is 384,000 tokens on deepseek-v4-flash and 64,000 tokens on gemini-3.1-pro-preview.
deepseek-v4-flash at 101.3 tokens/s and gemini-3.1-pro-preview at 79.5 tokens/s, measured as output throughput on AIHubMix — a separate metric from first-token latency.
deepseek-v4-flash accepts text input and supports tool calling, function calling, structured outputs and thinking; gemini-3.1-pro-preview accepts text, image, audio and video input and supports thinking, tool calling, function calling, structured outputs, web search, deep search and long context.
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Related model match-ups readers also look at.
AIHubMix